Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    negative and critical language directed towards individuals or groups, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spasm
    -0.50
     رع
    -0.48
    Plen
    -0.47
    idiv
    -0.46
    EMERGENCY
    -0.46
    orias
    -0.45
     verz
    -0.45
     gynhyrchwyd
    -0.44
     جذ
    -0.44
     pinta
    -0.43
    POSITIVE LOGITS
     insults
    1.24
     criticism
    1.22
     mocking
    1.15
     insult
    1.15
     dispar
    1.11
     attacks
    1.10
     ridicule
    1.08
     insulting
    1.08
     criticize
    1.07
     attack
    1.06
    Act Density 0.514%

    No Known Activations